Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "A rather largish update for everything time and timer related:

   - Cache footprint optimizations for both hrtimers and timer wheel

   - Lower the NOHZ impact on systems which have NOHZ or timer migration
     disabled at runtime.

   - Optimize run time overhead of hrtimer interrupt by making the clock
     offset updates smarter

   - hrtimer cleanups and removal of restrictions to tackle some
     problems in sched/perf

   - Some more leap second tweaks

   - Another round of changes addressing the 2038 problem

   - First step to change the internals of clock event devices by
     introducing the necessary infrastructure

   - Allow constant folding for usecs/msecs_to_jiffies()

   - The usual pile of clockevent/clocksource driver updates

  The hrtimer changes contain updates to sched, perf and x86 as they
  depend on them plus changes all over the tree to cleanup API changes
  and redundant code, which got copied all over the place.  The y2038
  changes touch s390 to remove the last non 2038 safe code related to
  boot/persistant clock"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (114 commits)
  clocksource: Increase dependencies of timer-stm32 to limit build wreckage
  timer: Minimize nohz off overhead
  timer: Reduce timer migration overhead if disabled
  timer: Stats: Simplify the flags handling
  timer: Replace timer base by a cpu index
  timer: Use hlist for the timer wheel hash buckets
  timer: Remove FIFO "guarantee"
  timers: Sanitize catchup_timer_jiffies() usage
  hrtimer: Allow hrtimer::function() to free the timer
  seqcount: Introduce raw_write_seqcount_barrier()
  seqcount: Rename write_seqcount_barrier()
  hrtimer: Fix hrtimer_is_queued() hole
  hrtimer: Remove HRTIMER_STATE_MIGRATE
  selftest: Timers: Avoid signal deadlock in leap-a-day
  timekeeping: Copy the shadow-timekeeper over the real timekeeper last
  clockevents: Check state instead of mode in suspend/resume path
  selftests: timers: Add leap-second timer edge testing to leap-a-day.c
  ntp: Do leapsecond adjustment in adjtimex read path
  time: Prevent early expiry of hrtimers[CLOCK_REALTIME] at the leap second edge
  ntp: Introduce and use SECS_PER_DAY macro instead of 86400
  ...

33 files changed, 1142 insertions, 1263 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index f2003b97ddc9..8e13f3e54ec3 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -51,9 +51,11 @@
 
 static struct workqueue_struct *perf_wq;
 
+typedef int (*remote_function_f)(void *);
+
 struct remote_function_call {
 	struct task_struct	*p;
-	int			(*func)(void *info);
+	remote_function_f	func;
 	void			*info;
 	int			ret;
 };
@@ -86,7 +88,7 @@ static void remote_function(void *data)
  *	    -EAGAIN - when the process moved away
  */
 static int
-task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
+task_function_call(struct task_struct *p, remote_function_f func, void *info)
 {
 	struct remote_function_call data = {
 		.p	= p,
@@ -110,7 +112,7 @@ task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
  *
  * returns: @func return value or -ENXIO when the cpu is offline
  */
-static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
+static int cpu_function_call(int cpu, remote_function_f func, void *info)
 {
 	struct remote_function_call data = {
 		.p	= NULL,
@@ -747,62 +749,31 @@ perf_cgroup_mark_enabled(struct perf_event *event,
 /*
  * function must be called with interrupts disbled
  */
-static enum hrtimer_restart perf_cpu_hrtimer_handler(struct hrtimer *hr)
+static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr)
 {
 	struct perf_cpu_context *cpuctx;
-	enum hrtimer_restart ret = HRTIMER_NORESTART;
 	int rotations = 0;
 
 	WARN_ON(!irqs_disabled());
 
 	cpuctx = container_of(hr, struct perf_cpu_context, hrtimer);
-
 	rotations = perf_rotate_context(cpuctx);
 
-	/*
-	 * arm timer if needed
-	 */
-	if (rotations) {
+	raw_spin_lock(&cpuctx->hrtimer_lock);
+	if (rotations)
 		hrtimer_forward_now(hr, cpuctx->hrtimer_interval);
-		ret = HRTIMER_RESTART;
-	}
-
-	return ret;
-}
-
-/* CPU is going down */
-void perf_cpu_hrtimer_cancel(int cpu)
-{
-	struct perf_cpu_context *cpuctx;
-	struct pmu *pmu;
-	unsigned long flags;
-
-	if (WARN_ON(cpu != smp_processor_id()))
-		return;
-
-	local_irq_save(flags);
-
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-
-		if (pmu->task_ctx_nr == perf_sw_context)
-			continue;
-
-		hrtimer_cancel(&cpuctx->hrtimer);
-	}
-
-	rcu_read_unlock();
+	else
+		cpuctx->hrtimer_active = 0;
+	raw_spin_unlock(&cpuctx->hrtimer_lock);
 
-	local_irq_restore(flags);
+	return rotations ? HRTIMER_RESTART : HRTIMER_NORESTART;
 }
 
-static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
+static void __perf_mux_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
 {
-	struct hrtimer *hr = &cpuctx->hrtimer;
+	struct hrtimer *timer = &cpuctx->hrtimer;
 	struct pmu *pmu = cpuctx->ctx.pmu;
-	int timer;
+	u64 interval;
 
 	/* no multiplexing needed for SW PMU */
 	if (pmu->task_ctx_nr == perf_sw_context)
@@ -812,31 +783,36 @@ static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
 	 * check default is sane, if not set then force to
 	 * default interval (1/tick)
 	 */
-	timer = pmu->hrtimer_interval_ms;
-	if (timer < 1)
-		timer = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER;
+	interval = pmu->hrtimer_interval_ms;
+	if (interval < 1)
+		interval = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER;
 
-	cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
+	cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval);
 
-	hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
-	hr->function = perf_cpu_hrtimer_handler;
+	raw_spin_lock_init(&cpuctx->hrtimer_lock);
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+	timer->function = perf_mux_hrtimer_handler;
 }
 
-static void perf_cpu_hrtimer_restart(struct perf_cpu_context *cpuctx)
+static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx)
 {
-	struct hrtimer *hr = &cpuctx->hrtimer;
+	struct hrtimer *timer = &cpuctx->hrtimer;
 	struct pmu *pmu = cpuctx->ctx.pmu;
+	unsigned long flags;
 
 	/* not for SW PMU */
 	if (pmu->task_ctx_nr == perf_sw_context)
-		return;
+		return 0;
 
-	if (hrtimer_active(hr))
-		return;
+	raw_spin_lock_irqsave(&cpuctx->hrtimer_lock, flags);
+	if (!cpuctx->hrtimer_active) {
+		cpuctx->hrtimer_active = 1;
+		hrtimer_forward_now(timer, cpuctx->hrtimer_interval);
+		hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
+	}
+	raw_spin_unlock_irqrestore(&cpuctx->hrtimer_lock, flags);
 
-	if (!hrtimer_callback_running(hr))
-		__hrtimer_start_range_ns(hr, cpuctx->hrtimer_interval,
-					 0, HRTIMER_MODE_REL_PINNED, 0);
+	return 0;
 }
 
 void perf_pmu_disable(struct pmu *pmu)
@@ -1935,7 +1911,7 @@ group_sched_in(struct perf_event *group_event,
 
 	if (event_sched_in(group_event, cpuctx, ctx)) {
 		pmu->cancel_txn(pmu);
-		perf_cpu_hrtimer_restart(cpuctx);
+		perf_mux_hrtimer_restart(cpuctx);
 		return -EAGAIN;
 	}
 
@@ -1982,7 +1958,7 @@ group_error:
 
 	pmu->cancel_txn(pmu);
 
-	perf_cpu_hrtimer_restart(cpuctx);
+	perf_mux_hrtimer_restart(cpuctx);
 
 	return -EAGAIN;
 }
@@ -2255,7 +2231,7 @@ static int __perf_event_enable(void *info)
 		 */
 		if (leader != event) {
 			group_sched_out(leader, cpuctx, ctx);
-			perf_cpu_hrtimer_restart(cpuctx);
+			perf_mux_hrtimer_restart(cpuctx);
 		}
 		if (leader->attr.pinned) {
 			update_group_times(leader);
@@ -6897,9 +6873,8 @@ static void perf_swevent_start_hrtimer(struct perf_event *event)
 	} else {
 		period = max_t(u64, 10000, hwc->sample_period);
 	}
-	__hrtimer_start_range_ns(&hwc->hrtimer,
-				ns_to_ktime(period), 0,
-				HRTIMER_MODE_REL_PINNED, 0);
+	hrtimer_start(&hwc->hrtimer, ns_to_ktime(period),
+		      HRTIMER_MODE_REL_PINNED);
 }
 
 static void perf_swevent_cancel_hrtimer(struct perf_event *event)
@@ -7200,6 +7175,8 @@ perf_event_mux_interval_ms_show(struct device *dev,
 	return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->hrtimer_interval_ms);
 }
 
+static DEFINE_MUTEX(mux_interval_mutex);
+
 static ssize_t
 perf_event_mux_interval_ms_store(struct device *dev,
 				 struct device_attribute *attr,
@@ -7219,17 +7196,21 @@ perf_event_mux_interval_ms_store(struct device *dev,
 	if (timer == pmu->hrtimer_interval_ms)
 		return count;
 
+	mutex_lock(&mux_interval_mutex);
 	pmu->hrtimer_interval_ms = timer;
 
 	/* update all cpuctx for this PMU */
-	for_each_possible_cpu(cpu) {
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
 		struct perf_cpu_context *cpuctx;
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
 
-		if (hrtimer_active(&cpuctx->hrtimer))
-			hrtimer_forward_now(&cpuctx->hrtimer, cpuctx->hrtimer_interval);
+		cpu_function_call(cpu,
+			(remote_function_f)perf_mux_hrtimer_restart, cpuctx);
 	}
+	put_online_cpus();
+	mutex_unlock(&mux_interval_mutex);
 
 	return count;
 }
@@ -7334,7 +7315,7 @@ skip_type:
 		lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
 		cpuctx->ctx.pmu = pmu;
 
-		__perf_cpu_hrtimer_init(cpuctx, cpu);
+		__perf_mux_hrtimer_init(cpuctx, cpu);
 
 		cpuctx->unique_pmu = pmu;
 	}
diff --git a/kernel/futex.c b/kernel/futex.c
index aacc706f85fc..ea6ca0bca525 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2064,11 +2064,8 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
 	queue_me(q, hb);
 
 	/* Arm the timer */
-	if (timeout) {
+	if (timeout)
 		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
-		if (!hrtimer_active(&timeout->timer))
-			timeout->task = NULL;
-	}
 
 	/*
 	 * If we have been removed from the hash list, then another task
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 30ec5b46cd8c..36573e96a477 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1182,11 +1182,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	set_current_state(state);
 
 	/* Setup the timer, when timeout != NULL */
-	if (unlikely(timeout)) {
+	if (unlikely(timeout))
 		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
-		if (!hrtimer_active(&timeout->timer))
-			timeout->task = NULL;
-	}
 
 	ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 32664347091a..013485fb2b06 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1375,9 +1375,9 @@ static void rcu_prepare_kthreads(int cpu)
  * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
  * any flavor of RCU.
  */
-int rcu_needs_cpu(unsigned long *delta_jiffies)
+int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 {
-	*delta_jiffies = ULONG_MAX;
+	*nextevt = KTIME_MAX;
 	return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)
 	       ? 0 : rcu_cpu_has_callbacks(NULL);
 }
@@ -1439,8 +1439,6 @@ module_param(rcu_idle_gp_delay, int, 0644);
 static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY;
 module_param(rcu_idle_lazy_gp_delay, int, 0644);
 
-extern int tick_nohz_active;
-
 /*
  * Try to advance callbacks for all flavors of RCU on the current CPU, but
  * only if it has been awhile since the last time we did so.  Afterwards,
@@ -1487,12 +1485,13 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
  *
  * The caller must have disabled interrupts.
  */
-int rcu_needs_cpu(unsigned long *dj)
+int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 {
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	unsigned long dj;
 
 	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) {
-		*dj = ULONG_MAX;
+		*nextevt = KTIME_MAX;
 		return 0;
 	}
 
@@ -1501,7 +1500,7 @@ int rcu_needs_cpu(unsigned long *dj)
 
 	/* If no callbacks, RCU doesn't need the CPU. */
 	if (!rcu_cpu_has_callbacks(&rdtp->all_lazy)) {
-		*dj = ULONG_MAX;
+		*nextevt = KTIME_MAX;
 		return 0;
 	}
 
@@ -1515,11 +1514,12 @@ int rcu_needs_cpu(unsigned long *dj)
 
 	/* Request timer delay depending on laziness, and round. */
 	if (!rdtp->all_lazy) {
-		*dj = round_up(rcu_idle_gp_delay + jiffies,
+		dj = round_up(rcu_idle_gp_delay + jiffies,
 			       rcu_idle_gp_delay) - jiffies;
 	} else {
-		*dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
+		dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
 	}
+	*nextevt = basemono + dj * TICK_NSEC;
 	return 0;
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f89ca9bcf42a..c9a707b59331 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -90,26 +90,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
-void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
-{
-	unsigned long delta;
-	ktime_t soft, hard, now;
-
-	for (;;) {
-		if (hrtimer_active(period_timer))
-			break;
-
-		now = hrtimer_cb_get_time(period_timer);
-		hrtimer_forward(period_timer, now, period);
-
-		soft = hrtimer_get_softexpires(period_timer);
-		hard = hrtimer_get_expires(period_timer);
-		delta = ktime_to_ns(ktime_sub(hard, soft));
-		__hrtimer_start_range_ns(period_timer, soft, delta,
-					 HRTIMER_MODE_ABS_PINNED, 0);
-	}
-}
-
 DEFINE_MUTEX(sched_domains_mutex);
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
@@ -355,12 +335,11 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
 
 #ifdef CONFIG_SMP
 
-static int __hrtick_restart(struct rq *rq)
+static void __hrtick_restart(struct rq *rq)
 {
 	struct hrtimer *timer = &rq->hrtick_timer;
-	ktime_t time = hrtimer_get_softexpires(timer);
 
-	return __hrtimer_start_range_ns(timer, time, 0, HRTIMER_MODE_ABS_PINNED, 0);
+	hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
 }
 
 /*
@@ -440,8 +419,8 @@ void hrtick_start(struct rq *rq, u64 delay)
 	 * doesn't make sense. Rely on vruntime for fairness.
 	 */
 	delay = max_t(u64, delay, 10000LL);
-	__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
-			HRTIMER_MODE_REL_PINNED, 0);
+	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
+		      HRTIMER_MODE_REL_PINNED);
 }
 
 static inline void init_hrtick(void)
@@ -639,13 +618,12 @@ void resched_cpu(int cpu)
  * selecting an idle cpu will add more delays to the timers than intended
  * (as that cpu's timer base may not be uptodate wrt jiffies etc).
  */
-int get_nohz_timer_target(int pinned)
+int get_nohz_timer_target(void)
 {
-	int cpu = smp_processor_id();
-	int i;
+	int i, cpu = smp_processor_id();
 	struct sched_domain *sd;
 
-	if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu))
+	if (!idle_cpu(cpu))
 		return cpu;
 
 	rcu_read_lock();
@@ -7126,8 +7104,6 @@ void __init sched_init_smp(void)
 }
 #endif /* CONFIG_SMP */
 
-const_debug unsigned int sysctl_timer_migration = 1;
-
 int in_sched_functions(unsigned long addr)
 {
 	return in_lock_functions(addr) ||
@@ -8163,10 +8139,8 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 
 	__refill_cfs_bandwidth_runtime(cfs_b);
 	/* restart the period timer (if active) to handle new period expiry */
-	if (runtime_enabled && cfs_b->timer_active) {
-		/* force a reprogram */
-		__start_cfs_bandwidth(cfs_b, true);
-	}
+	if (runtime_enabled)
+		start_cfs_bandwidth(cfs_b);
 	raw_spin_unlock_irq(&cfs_b->lock);
 
 	for_each_online_cpu(i) {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 392e8fb94db3..eac20c557a55 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -503,8 +503,6 @@ static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted)
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 	ktime_t now, act;
-	ktime_t soft, hard;
-	unsigned long range;
 	s64 delta;
 
 	if (boosted)
@@ -527,15 +525,9 @@ static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted)
 	if (ktime_us_delta(act, now) < 0)
 		return 0;
 
-	hrtimer_set_expires(&dl_se->dl_timer, act);
+	hrtimer_start(&dl_se->dl_timer, act, HRTIMER_MODE_ABS);
 
-	soft = hrtimer_get_softexpires(&dl_se->dl_timer);
-	hard = hrtimer_get_expires(&dl_se->dl_timer);
-	range = ktime_to_ns(ktime_sub(hard, soft));
-	__hrtimer_start_range_ns(&dl_se->dl_timer, soft,
-				 range, HRTIMER_MODE_ABS, 0);
-
-	return hrtimer_active(&dl_se->dl_timer);
+	return 1;
 }
 
 /*
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 704683cc9042..315c68e015d9 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -232,8 +232,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 #endif
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
-	SEQ_printf(m, "  .%-30s: %d\n", "tg->cfs_bandwidth.timer_active",
-			cfs_rq->tg->cfs_bandwidth.timer_active);
 	SEQ_printf(m, "  .%-30s: %d\n", "throttled",
 			cfs_rq->throttled);
 	SEQ_printf(m, "  .%-30s: %d\n", "throttle_count",
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 433061d984ea..40a7fcbf491e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3504,16 +3504,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	if (cfs_b->quota == RUNTIME_INF)
 		amount = min_amount;
 	else {
-		/*
-		 * If the bandwidth pool has become inactive, then at least one
-		 * period must have elapsed since the last consumption.
-		 * Refresh the global state and ensure bandwidth timer becomes
-		 * active.
-		 */
-		if (!cfs_b->timer_active) {
-			__refill_cfs_bandwidth_runtime(cfs_b);
-			__start_cfs_bandwidth(cfs_b, false);
-		}
+		start_cfs_bandwidth(cfs_b);
 
 		if (cfs_b->runtime > 0) {
 			amount = min(cfs_b->runtime, min_amount);
@@ -3662,6 +3653,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
 	long task_delta, dequeue = 1;
+	bool empty;
 
 	se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
 
@@ -3691,13 +3683,21 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	cfs_rq->throttled = 1;
 	cfs_rq->throttled_clock = rq_clock(rq);
 	raw_spin_lock(&cfs_b->lock);
+	empty = list_empty(&cfs_rq->throttled_list);
+
 	/*
 	 * Add to the _head_ of the list, so that an already-started
 	 * distribute_cfs_runtime will not see us
 	 */
 	list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
-	if (!cfs_b->timer_active)
-		__start_cfs_bandwidth(cfs_b, false);
+
+	/*
+	 * If we're the first throttled task, make sure the bandwidth
+	 * timer is running.
+	 */
+	if (empty)
+		start_cfs_bandwidth(cfs_b);
+
 	raw_spin_unlock(&cfs_b->lock);
 }
 
@@ -3812,13 +3812,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	if (cfs_b->idle && !throttled)
 		goto out_deactivate;
 
-	/*
-	 * if we have relooped after returning idle once, we need to update our
-	 * status as actually running, so that other cpus doing
-	 * __start_cfs_bandwidth will stop trying to cancel us.
-	 */
-	cfs_b->timer_active = 1;
-
 	__refill_cfs_bandwidth_runtime(cfs_b);
 
 	if (!throttled) {
@@ -3863,7 +3856,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	return 0;
 
 out_deactivate:
-	cfs_b->timer_active = 0;
 	return 1;
 }
 
@@ -3878,7 +3870,7 @@ static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC;
  * Are we near the end of the current quota period?
  *
  * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the
- * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of
+ * hrtimer base being cleared by hrtimer_start. In the case of
  * migrate_hrtimers, base is never cleared, so we are fine.
  */
 static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
@@ -3906,8 +3898,9 @@ static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b)
 	if (runtime_refresh_within(cfs_b, min_left))
 		return;
 
-	start_bandwidth_timer(&cfs_b->slack_timer,
-				ns_to_ktime(cfs_bandwidth_slack_period));
+	hrtimer_start(&cfs_b->slack_timer,
+			ns_to_ktime(cfs_bandwidth_slack_period),
+			HRTIMER_MODE_REL);
 }
 
 /* we know any runtime found here is valid as update_curr() precedes return */
@@ -4027,6 +4020,7 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
 {
 	struct cfs_bandwidth *cfs_b =
 		container_of(timer, struct cfs_bandwidth, slack_timer);
+
 	do_sched_cfs_slack_timer(cfs_b);
 
 	return HRTIMER_NORESTART;
@@ -4036,20 +4030,19 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 {
 	struct cfs_bandwidth *cfs_b =
 		container_of(timer, struct cfs_bandwidth, period_timer);
-	ktime_t now;
 	int overrun;
 	int idle = 0;
 
 	raw_spin_lock(&cfs_b->lock);
 	for (;;) {
-		now = hrtimer_cb_get_time(timer);
-		overrun = hrtimer_forward(timer, now, cfs_b->period);
-
+		overrun = hrtimer_forward_now(timer, cfs_b->period);
 		if (!overrun)
 			break;
 
 		idle = do_sched_cfs_period_timer(cfs_b, overrun);
 	}
+	if (idle)
+		cfs_b->period_active = 0;
 	raw_spin_unlock(&cfs_b->lock);
 
 	return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
@@ -4063,7 +4056,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	cfs_b->period = ns_to_ktime(default_cfs_period());
 
 	INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
-	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
 	cfs_b->period_timer.function = sched_cfs_period_timer;
 	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	cfs_b->slack_timer.function = sched_cfs_slack_timer;
@@ -4075,28 +4068,15 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	INIT_LIST_HEAD(&cfs_rq->throttled_list);
 }
 
-/* requires cfs_b->lock, may release to reprogram timer */
-void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force)
+void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 {
-	/*
-	 * The timer may be active because we're trying to set a new bandwidth
-	 * period or because we're racing with the tear-down path
-	 * (timer_active==0 becomes visible before the hrtimer call-back
-	 * terminates).  In either case we ensure that it's re-programmed
-	 */
-	while (unlikely(hrtimer_active(&cfs_b->period_timer)) &&
-	       hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) {
-		/* bounce the lock to allow do_sched_cfs_period_timer to run */
-		raw_spin_unlock(&cfs_b->lock);
-		cpu_relax();
-		raw_spin_lock(&cfs_b->lock);
-		/* if someone else restarted the timer then we're done */
-		if (!force && cfs_b->timer_active)
-			return;
-	}
+	lockdep_assert_held(&cfs_b->lock);
 
-	cfs_b->timer_active = 1;
-	start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period);
+	if (!cfs_b->period_active) {
+		cfs_b->period_active = 1;
+		hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
+		hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
+	}
 }
 
 static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 560d2fa623c3..7d7093c51f8d 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -18,19 +18,22 @@ static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
 {
 	struct rt_bandwidth *rt_b =
 		container_of(timer, struct rt_bandwidth, rt_period_timer);
-	ktime_t now;
-	int overrun;
 	int idle = 0;
+	int overrun;
 
+	raw_spin_lock(&rt_b->rt_runtime_lock);
 	for (;;) {
-		now = hrtimer_cb_get_time(timer);
-		overrun = hrtimer_forward(timer, now, rt_b->rt_period);
-
+		overrun = hrtimer_forward_now(timer, rt_b->rt_period);
 		if (!overrun)
 			break;
 
+		raw_spin_unlock(&rt_b->rt_runtime_lock);
 		idle = do_sched_rt_period_timer(rt_b, overrun);
+		raw_spin_lock(&rt_b->rt_runtime_lock);
 	}
+	if (idle)
+		rt_b->rt_period_active = 0;
+	raw_spin_unlock(&rt_b->rt_runtime_lock);
 
 	return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
 }
@@ -52,11 +55,12 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
 		return;
 
-	if (hrtimer_active(&rt_b->rt_period_timer))
-		return;
-
 	raw_spin_lock(&rt_b->rt_runtime_lock);
-	start_bandwidth_timer(&rt_b->rt_period_timer, rt_b->rt_period);
+	if (!rt_b->rt_period_active) {
+		rt_b->rt_period_active = 1;
+		hrtimer_forward_now(&rt_b->rt_period_timer, rt_b->rt_period);
+		hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED);
+	}
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d62b2882232b..aea7c1f393cb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -137,6 +137,7 @@ struct rt_bandwidth {
 	ktime_t			rt_period;
 	u64			rt_runtime;
 	struct hrtimer		rt_period_timer;
+	unsigned int		rt_period_active;
 };
 
 void __dl_clear_params(struct task_struct *p);
@@ -221,7 +222,7 @@ struct cfs_bandwidth {
 	s64 hierarchical_quota;
 	u64 runtime_expires;
 
-	int idle, timer_active;
+	int idle, period_active;
 	struct hrtimer period_timer, slack_timer;
 	struct list_head throttled_cfs_rq;
 
@@ -312,7 +313,7 @@ extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
 
 extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
-extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force);
+extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
 extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
 
 extern void free_rt_sched_group(struct task_group *tg);
@@ -1409,8 +1410,6 @@ static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
 static inline void sched_avg_update(struct rq *rq) { }
 #endif
 
-extern void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period);
-